Automation Of Method Research Articles

О практике развития некоторых элементов конвергентного образования в технологическом вузе

The article examines the experience of the Faculty of Humanities and its Center for Cognitive Psychology at the University of Technology in involving students in research and applied scientific projects through cooperation and integration of the humanities and technology departments of the University. The ideas of the transformation of the country's educational system and the change of its methodological, pedagogical and technological guidelines in response to modern challenges and risks are analyzed, primarily for the younger generation in need of social adaptation and deeper natural science and humanitarian training for professional and personal growth. The attempts to substantiate the definition of "convergent education" are analyzed. All of them are based on an understanding, to one degree or another, of an interdisciplinary methodological approach to the formation of educational programs, in order to overcome the highly professional training of specialists and avoid formalizing the content of educational material, taking into account the productive interaction of the fundamental component of humanitarian and professional knowledge, the use of modern methods of automation of various types of information activities using information and computer technologies (algorithmization of learning, information modeling). In general, the convergence of education is defined as a process of learning and upbringing, which is a consequence of the implementation of the modern educational paradigm aimed at understanding, rather than memorizing, education for change, the ability to withstand stress, live in a digital world, preserving humanity, sociability and collectivism, ensuring teamwork, preservation and development of the humanitarian and intellectual component "in the context of the interpenetration of sciences and technologies in the implementation of the convergence of real and virtual communications. The scientific and methodological basis for the development of convergent education at the first stage was the development of scientific and pedagogical practices. This can include the management of students' research activities (R&D), involving them in the development and implementation of various projects of scientific laboratories and centers of departments and faculties. The article summarizes some of the experience of the Center for Cognitive Psychology of the Faculty of Social Sciences and Humanities - SGT (until 2022 – ISGT– Institute) of the Federal State Educational Institution of Higher Education "K.G. Razumovsky Moscow State Technical University (PKU)", which was actively involved in the process of cluster formation in the conditions of the university's transformation into an innovative expert–analytical platform, the formation of an expert-educational cluster of excellence "NBICS-technologies of the food industry".

Development of automation and monitoring methods for narrow-gap hot-wire laser welding using camera images

AbstractIn this study, an image-based method was developed for hot-wire laser narrow gap welding. The welding process was monitored based on image information processed using semantic segmentation, a method of classifying images by pixel. To control the welding position, an experimental system was configured that automatically follows the welding position by recognizing the position of the welding groove from the image during welding. In monitoring weld defects, a method was developed to predict the lack of fusion occurring on the wall surface using brightness information near the wall surface. For the lack of fusion occurring at the bottom of the groove, a defect detection method was developed by monitoring the molten pool shape using semantic segmentation. Defects were generated by intentionally reducing the laser power, and the defects were monitored from images taken during processing. In the unstable state where the laser power was reduced, the shape in front of the molten pool became unstable, and the occurrence of defects was monitored by capturing the shape change. In conclusion, this research made it possible to control and monitor the welding process with a single camera.

Suggestion of a hybrid computational model to optimize EEG motor imagery signals classification

Brain-computer interfaces (BCIs) have proven to be innovative and promising technologies for human-machine interaction. However, distinguishing with relative precision between EEG motor signals generated by real or imagined movements of the left and right hands has still been a major challenge. By analyzing brain electrical signals and the processes of reading, processing, and interpreting data, the hybrid model suggested in this dissertation contributed to greater effectiveness of the algorithms, with accuracy above that normally found in most models present in the most recent literature. The experimental and observational research carried out in the creation of the methodology applied in this dissertation ensures the replication of automation methods, techniques, and algorithms, machine learning, and more specifically, in data preparation, feature extraction, signal classification, and obtaining results with greater accuracy for the implementation of brain-computer interfaces, BCIs. This dissertation opens new possibilities for future research and deepening of techniques, tools, and new experiments. With a premise to create personalized BCIs and trained specifically for individual pattern recognition, as they have shown greater potential results. Each human being is unique and has singular characteristics that distinguish them from all other beings.

On Digital Transformation Experience of the Order Fulfillment Process

The paper examines the process of order execution being won on a tender platform. Due to the short order fulfillment deadline, the work starts not at the moment of contract signing, but at the moment of winning the tender. This leads to additional risks of non-fulfillment of the order and the emergence of unfinished production. In the conditions of stock exchange prices in commodity markets, the process of the production cost determination becomes a more complex task, requiring daily cost reevaluation with the integration of heterogeneous information systems. Therefore, a transition from automation to digital transformation is required. The literature review on the issue of manufacturing enterprise digital transformation has been completed at work. The differences between the definitions of digitalization, automation and digital transformation are described. The most promising technologies for digital transformation are outlined. Based on the reviewed literature, the main problems of digital transformation, including managerial issues highlighted by the authors as the most important, are identified. The operations of several enterprises within one information space are described, indicating the information systems used. The process of creating an order on a tender platform for the examined manufacturing enterprise is detailed, as well as a detailed description of order creation. The issue of production cost determination in the conditions of order execution start prior to contract signing is discussed. The pressing issue of digital development of an industrial enterprise due to the transition to new information systems is presented. The problems of using current information systems in production are described. The market analysis of modern Russian, foreign, and open-source systems with a description of the issues of their application is provided. A method for unfinished product automation in a new order is proposed.

ANALYSIS AND SYSTEMATIZATION OF SOFTWARE INTERFACE DEVELOPMENT METHODS

The goal of this research is to analyze and systematize the methods used in software interface (SI) development, as well as to identify the optimal approaches and technologies for creating intuitive and user-friendly interfaces. In today's world, software interfaces play a crucial role in facilitating user interaction with software products, making their effective design essential. This study examines various SI design methodologies, including both classical and modern approaches, such as user-centered design (UCD), prototyping, usability testing, and adaptive design. Additionally, it explores principles of user interaction, including cognitive aspects and models of information perception, which contribute to the creation of more efficient and user-friendly interfaces.Special attention is given to contemporary technologies and tools, such as frameworks and libraries for interface development, as well as automation methods and the use of artificial intelligence in the SI design process. The research includes an analysis of successful SI implementations across various industries and reviews the latest trends in interface design. The findings are aimed at providing recommendations for selecting the most appropriate methods and technologies for SI development, depending on the project's specific requirements and the needs of end users.The key conclusions of this study may be valuable to software developers, user experience specialists, and interface designers in improving the quality of user interactions with software products. This work can also serve as a foundation for further research in the field of user interface development and optimization, contributing to the advancement of knowledge and practice in this area.

Development of Automation Methods to Design Special Welding Fixture Layouts

Development of Automation Methods to Design Special Welding Fixture Layouts

Do employee-friendly practices affect inventory leanness?

ABSTRACT We examine the impact of employee-friendly practices (i.e. employment quality, training and development, and employee turnover) on inventory leanness. We use the Empirical Leanness Indicator (ELI) as a proxy for inventory leanness. We employ OLS estimates to estimate our regressions while controlling for country, industry, and year-fixed effects and clustering standard errors at the firm level. We use alternative approaches to address endogeneity issues, such as the instrumental variable and the Heckman two-stage approaches. Our results suggest that employee-friendly practices improve inventory leanness. Our findings suggest that firms should invest in employee-friendly practices. This policy implication is of paramount importance for firms with more employees working in roles involving inventory (as opposed to automation or non-labour methods) and in environments with high dynamism and complexity. We also suggest that reputation mediates the relationship between employee-friendly practices and inventory leanness.

Imaging the adsorption sites of organic molecules on metallic surfaces by an adaptive tunnelling current feedback.

Atomic force microscopy (AFM) allows submolecular resolution imaging of organic molecules deposited on a surface by using CO-functionalized qPlus sensors under ultrahigh vacuum and low temperature conditions. However, the experimental determination of the adsorption sites of these organic molecules requires the precise identification of the atomic structure of the surface on which they are adsorbed. Here, we develop an automation method for AFM imaging that provides in a single image both, submolecular resolution on organic molecules and atomic resolution on the surrounding metallic surface. The method is based on an adaptive tunnelling current feedback system that is regulated according to the response of the AFM observables, which guarantees that both the molecules and the surface atoms are imaged under optimum conditions. Therewith, the approach is suitable for imaging adsorption sites of several adjacent and highly mobile molecules such as 2-iodotriphenylene on Ag(111) in a single scan. The proposed method with the adaptive feedback system facilitates statistical analysis of molecular adsorption geometries and could in the future contribute to autonomous AFM imaging as it adapts the feedback parameters depending on the sample properties.

RESEARCH ON ARTIFICIAL INTELLIGENCE TOOLS FOR AUTOMATING THE SOFTWARE TESTING PROCESS

The subject matter of the article is artificial intelligence (AI) tools for automating the software testing process. The rapid development of the software development industry in recent decades has led to a significant increase in competition in the IT technology market and, as a result, stricter requirements for corresponding products and services. AI-driven test automation is becoming increasingly relevant due to its ability to solve complex tasks that previously required significant human resources. The goal of the work is to investigate the possibilities of using AI technologies to automate manual testing processes, which will increase testing efficiency, reduce costs, and improve software quality. The following tasks were solved in the article: analysis of existing tools and approaches to test automation using AI; development of a conceptual model of a system that integrates AI into the testing process; exploring the potential of AI to automate various aspects of software testing, such as generating test scenarios, detecting defects, predicting errors, and automatically analyzing test results. The following methods are used: theoretical analysis of the literature and existing solutions in the field of test automation, experimental study of the effectiveness of the proposed test automation methods. The following results were obtained: the concept of a system that integrates AI technologies for automating software testing is presented. It has been found that the use of AI allows automating routine testing tasks, significantly reducing the number of human errors, and improving the quality of software products and the effectiveness of verification and validation processes. Conclusions: The development and implementation of AI-based testing automation systems are extremely relevant and promising. The use of AI technologies makes it possible to significantly increase the efficiency of testing, reduce the costs of its implementation, and improve the quality of software. The proposed approach to the development of an AI-based test automation system can be used as a basis for further research and development in this field.

Automation of systematic reviews of biomedical literature: a scoping review of studies indexed in PubMed

BackgroundThe demand for high-quality systematic literature reviews (SRs) for evidence-based medical decision-making is growing. SRs are costly and require the scarce resource of highly skilled reviewers. Automation technology has been proposed to save workload and expedite the SR workflow. We aimed to provide a comprehensive overview of SR automation studies indexed in PubMed, focusing on the applicability of these technologies in real world practice.MethodsIn November 2022, we extracted, combined, and ran an integrated PubMed search for SRs on SR automation. Full-text English peer-reviewed articles were included if they reported studies on SR automation methods (SSAM), or automated SRs (ASR). Bibliographic analyses and knowledge-discovery studies were excluded. Record screening was performed by single reviewers, and the selection of full text papers was performed in duplicate. We summarized the publication details, automated review stages, automation goals, applied tools, data sources, methods, results, and Google Scholar citations of SR automation studies.ResultsFrom 5321 records screened by title and abstract, we included 123 full text articles, of which 108 were SSAM and 15 ASR. Automation was applied for search (19/123, 15.4%), record screening (89/123, 72.4%), full-text selection (6/123, 4.9%), data extraction (13/123, 10.6%), risk of bias assessment (9/123, 7.3%), evidence synthesis (2/123, 1.6%), assessment of evidence quality (2/123, 1.6%), and reporting (2/123, 1.6%). Multiple SR stages were automated by 11 (8.9%) studies. The performance of automated record screening varied largely across SR topics. In published ASR, we found examples of automated search, record screening, full-text selection, and data extraction. In some ASRs, automation fully complemented manual reviews to increase sensitivity rather than to save workload. Reporting of automation details was often incomplete in ASRs.ConclusionsAutomation techniques are being developed for all SR stages, but with limited real-world adoption. Most SR automation tools target single SR stages, with modest time savings for the entire SR process and varying sensitivity and specificity across studies. Therefore, the real-world benefits of SR automation remain uncertain. Standardizing the terminology, reporting, and metrics of study reports could enhance the adoption of SR automation techniques in real-world practice.

Medical Image Classification using a Many to Many Relation, Multilayered Fuzzy Systems and AI

One of the research gaps in the medical sciences is the study of orphan diseases or rare diseases, due to limited data availability of rare diseases. Our previous study addressed this successfully by developing an Artificial Intelligence (AI)-based medical image classification method using a multilayer fuzzy approach (MFA), for detecting and classifying image abnormalities for large and very small datasets. A fuzzy system is an AI system used to handle imprecise data. There are more than three types of fuzziness in any image data set: 1) due to a projection of a 3D object on a 2D surface, 2) due to the digitalization of the scan, and 3) conversion of the digital image to grayscale, and more. Thus, this was referred to in the previous study as a multilayer fuzzy system, since fuzziness arises from multiple sources. The method used in MFA involves comparing normal images containing abnormalities with the same kind of image without abnormalities, yielding a similarity measure percentage that, when subtracted from a hundred, reveals the abnormality. However, relying on a single standard image in the MFA reduces efficiency, since images vary in contrast, lighting, and patient demographics, impacting similarity percentages. To mitigate this, the current study focused on developing a more robust medical image classification method than MFA, using a many-to-many relation and a multilayer fuzzy approach (MCM) that employs multiple diverse standard images to compare with the abnormal image. For each abnormal image, the average similarity was calculated across multiple normal images, addressing issues encountered with MFA, and enhancing versatility. In this study, an AI-based method of image analysis automation that utilizes fuzzy systems was applied to a cancer data set for the first time. MCM proved to be highly efficient in detecting the abnormality in all types of images and sample sizes and surpassed the gold standard, the convolutional neural network (CNN), in detecting the abnormality in images from a very small data set. Moreover, MCM detects and classifies abnormality without any training, validation, or testing steps for large and small data sets. Hence, MCM may be used to address one of the research gaps in medicine, which detects, quantifies, and classifies images related to rare diseases with small data sets. This has the potential to assist a physician with early detection, diagnosis, monitoring, and treatment planning of several diseases, especially rare diseases.

Application of the Multi-Threading Method and Python Script for the Automate of Network

In recent times, there has been a noticeable surge in the inclination towards the implementation of network automation solutions. This trend is driven by the objective of optimizing network availability within the context of hybrid data center networks, which are becoming increasingly prevalent. Reliability, performance, scalability, and minimal resource overhead are crucial solution design characteristics that significantly impact the decision- making process regarding adoption. Recent research has shown that 90% of network outages happen because of human factors and 69% of respondents manage their network with manual method. That high human error of up to 90%, occurs when configuring network devices using manual method. These problems had a negative impact on the functioning of the organization and were harmful to the user. In this research, we investigate solutions to reduce network outage that caused human error using network automation using the Python programming language and multi-threading method. This network automation will reduce configuration time, eliminate human error, and significantly increase efficiency. The aim of this research is to investigate the efficacy of network automation using Python and multi-threading to reduce network outages.The method used in this research is a parallel or multi-tread execution process method using GNS3 as network simulator. Based on experimental results, the multi- thread automation approach is significantly faster than both the serial automation method (67 seconds) and the manual method (248 seconds), this method requiring only 41 seconds to configure all Cisco router devices. If you're looking for speed, look no farther than the multi- thread automation approach, which is 6 times quicker than the manual method and 3.7 times quicker than the serial automation approach. The findings of this study have substantial and immediate implications for the ability of network engineers to speed up the configuration of networks and lower the rate of human error in doing so.

The automation of the processes of students’ reporting documentation standard control: The software solution concept

Reporting documentation is one of the assessment tools used to verify the students’ mastery of several universal, general professional, and vocational competencies, reflecting the ability to search, critically analyze, and synthesize information, as well as the ability to design methodological materials and develop technical documents related to professional activities. Mastering the relevant competencies can be assessed by the results of analyzing the report text and controlling the compliance of documents with requirements to the design, accompanied by a set of standard checks. Such standard control does not imply any variability in the assessment and therefore has prospects for automation. The introduction of a software solution aimed at automating the processes of standard control will reduce the time spent on checking the reporting documentation and the formation of recommendations for students to correct the detected inconsistencies.The article analyzes the most common errors in the design of students’ reporting documentation on the results of internships, compiles a classification of errors, and suggests methods for detecting each type of non-compliance with the requirements to the design of documents. The concept of the software solution for automation of standard reporting documentation control, which offers a realization of the proposed methods and creates interfaces for interaction with users, is created using the principle of modularity. The results of the research presented in the article demonstrate the potential of applying automation methods to the tasks of checking students’ reporting documents.

The model of hyper- and hypopigmented structureless areas recognition in the pigmented skin neoplasms

Skin melanoma – dangerous oncological disease which demand a differential diagnostics by clinical algorithms. In order to decrease a subjectivity and increase an accuracy of the medical diagnostics the methods of automation and artificial intelligence are used. There are no common approach to clinical algorithms automation and the topic of a common model of recognition of two variations of the algorithm “modified pattern analysis” important element “structureless areas” is not enough studied. This work is dedicated to development of the model of recognition of hyperpigmented and hypopigmented structureless areas of pigmented skin neoplasms. In the result of the study the developed model provide the possibility to recognize both variations of structureless areas and it’s adequateness if verified in the experiment that includes the processing of 400 images that contain structureless areas. The model accuracy was 83%. The model could be adjusted in future by the increase of the number of image characteristics taken into study and by the increase of the experimental set of images.

An AI-Based Approach for Automating Penetration Testing

Abstract: Cyber penetration testing (pen-testing) is important in revealing possible weaknesses and breaches in network systems that can ultimately help in curbing cybercrimes. Nevertheless, even with the current drive to mechanize pen- testing, there are still a number of challenges which include incomplete frameworks and low precision in automation methods. This paper aims at addressing them by suggesting hybrid AI-based automation framework specifically for Pen- Testing through integration of smart algorithms and automated tools. As indicated by recent studies, it goes further into proposing a holistic approach towards maximizing the efficiency as well as effectiveness of Pen-Testing processes. Furthermore, it also identifies the need for machine learning techniques such as reinforcement learning and deep reinforcement learning for automating Pen-Testing activities. MITRE ATT&CK Framework being utilized within the proposed model imitates real-life cyber-attacks and exploits hence facilitating automated testing across diverse target networks. Based on comparison with manual penetration testing reports, this study reviews how effective the new automated method is when compared to old ways used in manual penetration tests while providing some direction for future developments along with suggestions in the field of self- governing intrusion detection systems (IDS)

Diagnostic accuracy of automation and non-automation techniques for identifying Burkholderia pseudomallei: A systematic review and meta-analysis

BackgroundBurkholderia pseudomallei, a Gram-negative pathogen, causes melioidosis. Although various clinical laboratory identification methods exist, culture-based techniques lack comprehensive evaluation. Thus, this systematic review and meta-analysis aimed to assess the diagnostic accuracy of culture-based automation and non-automation methods. MethodsData were collected via PubMed/MEDLINE, EMBASE, and Scopus using specific search strategies. Selected studies underwent bias assessment using QUADAS-2. Sensitivity and specificity were computed, generating pooled estimates. Heterogeneity was assessed using I2 statistics. ResultsThe review encompassed 20 studies with 2988 B. pseudomallei samples and 753 non-B. pseudomallei samples. Automation-based methods, particularly with updating databases, exhibited high pooled sensitivity (82.79%; 95% CI 64.44–95.85%) and specificity (99.94%; 95% CI 98.93–100.00%). Subgroup analysis highlighted superior sensitivity for updating-database automation (96.42%, 95% CI 90.01–99.87%) compared to non-updating (3.31%, 95% CI 0.00–10.28%), while specificity remained high at 99.94% (95% CI 98.93–100%). Non-automation methods displayed varying sensitivity and specificity. In-house latex agglutination demonstrated the highest sensitivity (100%; 95% CI 98.49–100%), followed by commercial latex agglutination (99.24%; 95% CI 96.64–100%). However, API 20E had the lowest sensitivity (19.42%; 95% CI 12.94–28.10%). Overall, non-automation tools showed sensitivity of 88.34% (95% CI 77.30–96.25%) and specificity of 90.76% (95% CI 78.45–98.57%). ConclusionThe study underscores automation's crucial role in accurately identifying B. pseudomallei, supporting evidence-based melioidosis management decisions. Automation technologies, especially those with updating databases, provide reliable and efficient identification.

Machine and Deep Learning Implementations for Heritage Building Information Modelling: A Critical Review of Theoretical and Applied Research

Research domain and Problem: HBIM modelling from point cloud data has become a crucial research topic in the last decade since it is potentially considered as the central data model paving the way for the digital heritage practice beyond digitization. Reality Capture technologies such as terrestrial laser scanning, drone-mounted LiDAR sensors and photogrammetry enable the reality capture with a sub-millimetre accurate point cloud file that can be used as a reference file for Heritage Building Information Modelling (HBIM). However, HBIM modelling from the point cloud data of heritage buildings is mainly manual, error-prone, and time-consuming. Furthermore, image processing techniques are insufficient for classification and segmentation of point cloud data to speed up and enhance the current workflow for HBIM modelling. Due to the challenges and bottlenecks in the scan-to-HBIM process, which is commonly criticized as complex with its bespoke requirements, semantic segmentation of point clouds is gaining popularity in the literature. Research Aim and Methodology: Therefore, this paper aims to provide a thorough critical review of Machine Learning and Deep Learning methods for point cloud segmentation, classification, and BIM geometry automation for cultural heritage case study applications. Research findings: This paper files the challenges of HBIM practice and the opportunities for semantic point cloud segmentation found across academic literature in the last decade. Beyond definitions and basic occurrence statistics, this paper discusses the success rates and implementation challenges of machine and deep learning classification methods. Research value and contribution: This paper provides a holistic review of point cloud segmentation and its potential for further development and application in the Cultural Heritage sector. The critical analysis provides insight into the current state-of-the-art methods and advises on their suitability for HBIM projects. The review has identified highly original threads of research, which hold the potential to significantly influence practice and further applied research.

Modified Levey-Jennings Chart with Robust Estimator: A Case of Semiconductor Manufacturing Process

In the era of Industrial Revolution 4.0 and smart manufacturing, the development and deployment of control charts used in the semiconductor industry need to be automated. Consequently, artificial intelligence-based automation methods typically encompass the deployment of statistical software such as JMP. Automation involves frequent dataset updates; the control limits are recalculated as the parameters change (non-stationary behaviour). This requires the user to define the control chart type before its deployment on the production floor. An initially normally distributed dataset may be skewed during the process owing to the influence of outliers. If a user selects a chart based on normality assumptions, detecting a process-mean shift may be impossible if the recalculated limit fluctuates. In the semiconductor industry, a process-mean shift occurs owing to special cause variations in the process. This signals process deterioration, which may affect the quality of the product. It is unknown when outliers will affect the equilibrium of normality assumptions; therefore, it is important to develop an automated, robust control chart that can detect special cause variations under non-stationary conditions. This study proposes the use of Huber’s M-estimators in the Levey-Jennings chart to detect special cause variations in a semiconductor manufacturing process. This study computes the robust M-estimates of all available samples to calculate the new limits in the Levey-Jennings chart. This new chart is referred to as the modified Levey-Jennings with a robust Huber M-estimator (MLVHM). Using production data from Dominant Opto Technologies Sdn. Bhd., Malaysia, a statistical comparison of the MLVHM and Levey-Jennings charts was performed. While the MLVHM is stable, the absolute difference in dispersion between the two charts ranges between 25.26% and 47.91% owing to standard deviation variation in the Levey-Jennings chart in non-stationary situations with outliers. The study concludes that the MLVHM chart is robust and suitable for industrial automatic flow applications.

IoT workload offloading efficient intelligent transport system in federated ACNN integrated cooperated edge-cloud networks

Intelligent transport systems (ITS) provide various cooperative edge cloud services for roadside vehicular applications. These applications offer additional diversity, including ticket validation across transport modes and vehicle and object detection to prevent road collisions. Offloading among cooperative edge and cloud networks plays a key role when these resources constrain devices (e.g., vehicles and mobile) to offload their workloads for execution. ITS used different machine learning and deep learning methods for decision automation. However, the self-autonomous decision-making processes of these techniques require significantly more time and higher accuracy for the aforementioned applications on the road-unit side. Thus, this paper presents the new offloading ITS for IoT vehicles in cooperative edge cloud networks. We present the augmented convolutional neural network (ACNN) that trains the workloads on different edge nodes. The ACNN allows users and machine learning methods to work together, making decisions for offloading and scheduling workload execution. This paper presents an augmented federated learning scheduling scheme (AFLSS). An algorithmic method called AFLSS comprises different sub-schemes that work together in the ITS paradigm for IoT applications in transportation. These sub-schemes include ACNN, offloading, scheduling, and security. Simulation results demonstrate that, in terms of accuracy and total time for the considered problem, the AFLSS outperforms all existing methods.

Large language model based agent for process planning of fiber composite structures

Process planning is a crucial activity, connecting product development and manufacturing of fiber composite structures. Recently published Large Language Models (LLM) promise more flexible and autonomous workflows compared to state of the art automation methods. An autonomous agent for process planning of fiber composite structures is implemented with the LangChain framework, based on OpenAI’s GPT-4 language model. The agent is equipped with deterministic tools which encode a-priori process planning knowledge. It can handle different process planning problems, such as cycle time estimation and resource allocation. Combinations thereof are solved through executing a multi-step solution path.